Related Experiment Video
Updated: Jan 8, 2026
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.5K
Artificial Intelligence-Based Delirium Prediction Model for Post-Cardiac Surgery Patients: A Scoping Review
Centao Qin1,2, Lu Zeng1,2, Jinbo Zhang1,2
1Nursing Department, Affiliated Hospital of Zunyi Medical University, Zunyi, China.
Journal of Advanced Nursing
|December 18, 2025
Summary
Artificial intelligence (AI) models show promise for predicting postoperative delirium in cardiac surgery patients. Further research should focus on clinical integration and validation for improved patient outcomes.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Medicine
- Cardiology
Background:
- Postoperative delirium is a frequent complication after cardiac surgery, impacting patient prognosis.
- Artificial intelligence (AI) offers potential for predicting and assessing delirium risk in clinical settings.
Purpose of the Study:
- To conduct a scoping review of AI-based prediction models for post-cardiac surgery delirium.
- To offer insights and recommendations for clinical practice and future research.
Main Methods:
- A systematic literature search was performed across eight databases following PRISMA-ScR guidelines.
- Data extraction focused on study characteristics, delirium assessment, predictive factors, and AI models.
- Ten studies involving 11,702 participants were included in the review.
Main Results:
- Postoperative delirium incidence varied from 5.56% to 34%.
- Key predictors included age, cardiopulmonary bypass duration, cerebrovascular disease, and pain scores.
- Random Forest models demonstrated the highest efficacy (50%), followed by XGBoost (30%) and Artificial Neural Networks (20%).
Conclusions:
- AI-based models demonstrate potential for predicting delirium after cardiac surgery.
- Future research should prioritize clinical workflow integration, multicenter external validation, and dynamic variable incorporation.
